On vision transformer for ultra-short-term forecasting of photovoltaic generation using sky images

被引:4
|
作者
Xu, Shijie [1 ]
Zhang, Ruiyuan [2 ]
Ma, Hui [1 ]
Ekanayake, Chandima [1 ]
Cui, Yi [3 ]
机构
[1] Univ Queensland, Sch Informat Technol & Elect Engn, Brisbane 4072, Australia
[2] Hong Kong Univ Sci & Technol, Kowloon, Clear Water Bay, Hong Kong, Peoples R China
[3] Univ Southern Queensland, Brisbane, Australia
关键词
Deep learning; Forecasting; Image processing; Photovoltaic; Vision transformers; POWER; MODEL;
D O I
10.1016/j.solener.2023.112203
中图分类号
TE [石油、天然气工业]; TK [能源与动力工程];
学科分类号
0807 ; 0820 ;
摘要
An accurate photovoltaic (PV) generation forecasting is important for grid scheduling and dispatching. However, ultra-short-term PV generation forecasting is rather challenging because weather conditions may change significantly in a short time period largely due to the dynamics and movement of clouds above a solar PV farm. For monitoring clouds above the solar PV farm, ground-based whole-sky cameras (Sky-Imagers) have been installed. This paper develops a novel cloud image-based ultra-short-term forecasting framework. Within the framework, an integration of the Vision Transformer (ViT) model and the Gated Recurrent Unit (GRU) encoder is designed for the high-dimensional latent feature analysis. A Multi-Layer Perception (MLP) is employed to generate the one-step-ahead PV generation forecasting. Numeric experiments are conducted using real-world solar PV datasets. The results show that the proposed framework and algorithms can achieve higher accuracy compared to several baseline methods for ultra-short-term PV generation forecasting.
引用
收藏
页数:12
相关论文
共 50 条
  • [21] Ultra-short-term Prediction of Photovoltaic Power Generation Considering Cloud Cover
    Bai J.
    Dong C.
    Wang Z.
    Jiang J.
    Wang B.
    Liu G.
    Gaodianya Jishu/High Voltage Engineering, 2023, 49 (01): : 159 - 169
  • [22] Ultra-short-term Prediction of Photovoltaic Power Generation Based on Digital Twins
    Sun R.
    Wang L.
    Wang Y.
    Ding R.
    Xu H.
    Wang J.
    Li Q.
    Dianwang Jishu/Power System Technology, 2021, 45 (04): : 1258 - 1264
  • [23] Enhanced Ultra-Short-Term PV Forecasting Using Sky Imagers: Integrating MCR and Cloud Cover Estimation
    Mamaya Photovoltaic Branch of Guizhou Beipanjiang Electric Power Co., Ltd., Guiyang
    550081, China
    不详
    550081, China
    不详
    430023, China
    Energies, 2025, 18 (01)
  • [24] Power forecasting of ultra-short-term photovoltaic station based on NWP similarity analysis
    Zhang S.
    Dong L.
    Ji D.
    Hao Y.
    Zhang X.
    Taiyangneng Xuebao/Acta Energiae Solaris Sinica, 2022, 43 (04): : 142 - 147
  • [25] Ultra-short-term Prediction of Self-identifying Photovoltaic Based on Sky Cloud Chart
    Chai M.
    Xia F.
    Zhang H.
    Lu J.
    Cui C.
    Ma B.
    Dianwang Jishu/Power System Technology, 2021, 45 (03): : 1023 - 1031
  • [26] The ultra-short-term photovoltaic power prediction based on multi-exposure high-resolution total sky images using deep learning
    Bo, Yaolong
    Xia, Yanghong
    Ni, Yini
    Liu, Kejia
    Wei, Wei
    ENERGY REPORTS, 2023, 9 : 123 - 133
  • [27] Bus ultra-short-term load forecasting considering the impact of distributed photovoltaic power supply
    Yu, Changyong
    Zhang, Mingli
    Hu, Qiankun
    Zhu, Heyan
    Jiang, Li
    Nan, Zhe
    Li, Fang
    2019 5TH INTERNATIONAL CONFERENCE ON ENVIRONMENTAL SCIENCE AND MATERIAL APPLICATION, 2020, 440
  • [28] The Method for Photovoltaic Module Temperature Ultra-short-term Forecasting Based on RBF Neural Network
    Cheng, Xu
    Chen, Furong
    Yu, Bingxia
    Zhang, Xuesong
    2016 CHINA INTERNATIONAL CONFERENCE ON ELECTRICITY DISTRIBUTION (CICED), 2016,
  • [29] Improving ultra-short-term photovoltaic power forecasting using a novel sky-image-based framework considering spatial-temporal feature interaction
    Zang, Haixiang
    Chen, Dianhao
    Liu, Jingxuan
    Cheng, Lilin
    Sun, Guoqiang
    Wei, Zhinong
    ENERGY, 2024, 293
  • [30] Short-Term Photovoltaic Power Plant Output Forecasting Using Sky Images and Deep Learning
    Jakoplic, Alen
    Frankovic, Dubravko
    Havelka, Juraj
    Bulat, Hrvoje
    ENERGIES, 2023, 16 (14)